3D Chemical Similarity Networks for Structure-Based Target Prediction and Scaffold Hopping

Algorithm for Efficient Superposition and Clustering of Molecular Assemblies Using the Branch-and-Bound Method

The root-mean-square deviation (RMSD) is one of the most common metrics for comparing the similarity of three-dimensional chemical structures. The chemical structure similarity plays an important role in data chemistry because it is closely related to chemical reactivity, physical properties, and bioactivity. Despite the wide applicability of the RMSD, the simultaneous determination of atom mapping and spatial superposition of RMSD remains a challenging problem to solve in polynomial time. We introduce an algorithm called mobbRMSD, which is formulated in molecular-oriented coordinates and uses the branch-and-bound method to obtain an exact solution for the RMSD. mobbRMSD can efficiently handle a wide range of chemical systems, such as molecular liquids, solute solvations, and self-assembly of large molecules, using chemical knowledge such as atom types, chemical bonding, and chirality. In benchmarks involving small molecular aggregates, mobbRMSD extends the limiting system size of existing exact solution methods by almost twice. Furthermore, mobbRMSD demonstrated the ability to analyze the structural similarity of large molecular micelles, which has been difficult with previous methods. We also propose a mobbRMSD-based structural clustering method designed for molecular dynamics trajectories, which improves the computational cost of branch-and-bound methods to asymptotically average the polynomial time as the number of data increases. Our algorithm is freely available at https://github.com/yymmt742/mobbrmsd.

Next-Gen Therapeutics: Pioneering Drug Discovery with iPSCs, Genomics, AI, and Clinical Trials in a Dish

In the high-stakes arena of drug discovery, the journey from bench to bedside is hindered by a daunting 92% failure rate, primarily due to unpredicted toxicities and inadequate therapeutic efficacy in clinical trials. The FDA Modernization Act 2.0 heralds a transformative approach, advocating for the integration of alternative methods to conventional animal testing, including cell-based assays that employ human induced pluripotent stem cell (iPSC)-derived organoids, and organ-on-a-chip technologies, in conjunction with sophisticated artificial intelligence (AI) methodologies. Our review explores the innovative capacity of iPSC-derived clinical trial in a dish models designed for cardiovascular disease research. We also highlight how integrating iPSC technology with AI can accelerate the identification of viable therapeutic candidates, streamline drug screening, and pave the way toward more personalized medicine. Through this, we provide a comprehensive overview of the current landscape and future implications of iPSC and AI applications being navigated by the research community and pharmaceutical industry.

Molecular similarity: Theory, applications, and perspectives

Molecular similarity pervades much of our understanding and rationalization of chemistry. This has become particularly evident in the current data-intensive era of chemical research, with similarity measures serving as the backbone of many Machine Learning (ML) supervised and unsupervised procedures. Here, we present a discussion on the role of molecular similarity in drug design, chemical space exploration, chemical "art" generation, molecular representations, and many more. We also discuss more recent topics in molecular similarity, like the ability to efficiently compare large molecular libraries.

The changing scenario of drug discovery using AI to deep learning: Recent advancement, success stories, collaborations, and challenges

Due to the transformation of artificial intelligence (AI) tools and technologies, AI-driven drug discovery has come to the forefront. It reduces the time and expenditure. Due to these advantages, pharmaceutical industries are concentrating on AI-driven drug discovery. Several drug molecules have been discovered using AI-based techniques and tools, and several newly AI-discovered drug molecules have already entered clinical trials. In this review, we first present the data and their resources in the pharmaceutical sector for AI-driven drug discovery and illustrated some significant algorithms or techniques used for AI and ML which are used in this field. We gave an overview of the deep neural network (NN) models and compared them with artificial NNs. Then, we illustrate the recent advancement of the landscape of drug discovery using AI to deep learning, such as the identification of drug targets, prediction of their structure, estimation of drug-target interaction, estimation of drug-target binding affinity, design of de novo drug, prediction of drug toxicity, estimation of absorption, distribution, metabolism, excretion, toxicity; and estimation of drug-drug interaction. Moreover, we highlighted the success stories of AI-driven drug discovery and discussed several collaboration and the challenges in this area. The discussions in the article will enrich the pharmaceutical industry.

Polypharmacology prediction: the long road toward comprehensively anticipating small-molecule selectivity to de-risk drug discovery

INTRODUCTION

Small molecules often bind to multiple targets, a behavior termed polypharmacology. Anticipating polypharmacology is essential for drug discovery since unknown off-targets can modulate safety and efficacy - profoundly affecting drug discovery success. Unfortunately, experimental methods to assess selectivity present significant limitations and drugs still fail in the clinic due to unanticipated off-targets. Computational methods are a cost-effective, complementary approach to predict polypharmacology.

AREAS COVERED

This review aims to provide a comprehensive overview of the state of polypharmacology prediction and discuss its strengths and limitations, covering both classical cheminformatics methods and bioinformatic approaches. The authors review available data sources, paying close attention to their different coverage. The authors then discuss major algorithms grouped by the types of data that they exploit using selected examples.

EXPERT OPINION

Polypharmacology prediction has made impressive progress over the last decades and contributed to identify many off-targets. However, data incompleteness currently limits most approaches to comprehensively predict selectivity. Moreover, our limited agreement on model assessment challenges the identification of the best algorithms - which at present show modest performance in prospective real-world applications. Despite these limitations, the exponential increase of multidisciplinary Big Data and AI hold much potential to better polypharmacology prediction and de-risk drug discovery.

A Photochemical Strategy for the Conversion of Nitroarenes into Rigidified Pyrrolidine Analogues

Bicyclic amines are important motifs for the preparation of bioactive materials. These species have well-defined exit vectors that enable accurate disposition of substituents toward specific areas of chemical space. Of all possible skeletons, the 2-azabicyclo[3.2.0]heptane framework is virtually absent from MedChem libraries due to a paucity of synthetic methods for its preparation. Here, we report a modular synthetic strategy that utilizes nitroarenes as flat and easy-to-functionalize feedstocks for the assembly of these sp3-rich materials. Mechanistically, this approach exploits two concomitant photochemical processes that sequentially ring-expand the nitroarene into an azepine and then fold it into a rigid bicycle pyrroline by means of singlet nitrene-mediated nitrogen insertion and excited-state-4π electrocyclization. A following hydrogenolysis provides, with full diastereocontrol, the desired bicyclic amine derivatives whereby the aromatic substitution pattern has been translated into the one of the three-dimensional heterocycle. These molecules can be considered rigid pyrrolidine analogues with a well-defined orientation of their substituents. Furthermore, unsupervised clustering of an expansive virtual database of saturated N-heterocycles revealed these derivatives as effective isosteres of rigidified piperidines. Overall, this platform enables the conversion of nitroarene feedstocks into complex sp3-rich heterocycles of potential interest to drug development.

AI-powered therapeutic target discovery

Disease modeling and target identification are the most crucial initial steps in drug discovery, and influence the probability of success at every step of drug development. Traditional target identification is a time-consuming process that takes years to decades and usually starts in an academic setting. Given its advantages of analyzing large datasets and intricate biological networks, artificial intelligence (AI) is playing a growing role in modern drug target identification. We review recent advances in target discovery, focusing on breakthroughs in AI-driven therapeutic target exploration. We also discuss the importance of striking a balance between novelty and confidence in target selection. An increasing number of AI-identified targets are being validated through experiments and several AI-derived drugs are entering clinical trials; we highlight current limitations and potential pathways for moving forward.

Computational Approaches to the Rational Design of Tubulin-Targeting Agents

Microtubules are highly dynamic polymers of α,β-tubulin dimers which play an essential role in numerous cellular processes such as cell proliferation and intracellular transport, making them an attractive target for cancer and neurodegeneration research. To date, a large number of known tubulin binders were derived from natural products, while only one was developed by rational structure-based drug design. Several of these tubulin binders show promising in vitro profiles while presenting unacceptable off-target effects when tested in patients. Therefore, there is a continuing demand for the discovery of safer and more efficient tubulin-targeting agents. Since tubulin structural data is readily available, the employment of computer-aided design techniques can be a key element to focus on the relevant chemical space and guide the design process. Due to the high diversity and quantity of structural data available, we compiled here a guide to the accessible tubulin-ligand structures. Furthermore, we review different ligand and structure-based methods recently used for the successful selection and design of new tubulin-targeting agents.

Concepts and applications of chemical fingerprint for hit and lead screening

Molecular fingerprints are used to represent chemical (structural, physicochemical, etc.) properties of large-scale chemical sets in a low computational cost way. They have a prominent role in transforming chemical data sets into consistent input formats (bit strings or numeric values) suitable for in silico approaches. In this review, we summarize and classify common and state-of-the-art fingerprints into eight different types (dictionary based, circular, topological, pharmacophore, protein-ligand interaction, shape based, reinforced, and multi). We also highlight applications of fingerprints in early drug research and development (R&D). Thus, this review provides a guide for the selection of appropriate fingerprints of compounds (or ligand-protein complexes) for use in drug R&D.

Random-forest model for drug-target interaction prediction via Kullbeck-Leibler divergence

Virtual screening has significantly improved the success rate of early stage drug discovery. Recent virtual screening methods have improved owing to advances in machine learning and chemical information. Among these advances, the creative extraction of drug features is important for predicting drug–target interaction (DTI), which is a large-scale virtual screening of known drugs. Herein, we report Kullbeck–Leibler divergence (KLD) as a DTI feature and the feature-driven classification model applicable to DTI prediction. For the purpose, E3FP three-dimensional (3D) molecular fingerprints of drugs as a molecular representation allow the computation of 3D similarities between ligands within each target (Q–Q matrix) to identify the uniqueness of pharmacological targets and those between a query and a ligand (Q–L vector) in DTIs. The 3D similarity matrices are transformed into probability density functions via kernel density estimation as a nonparametric estimation. Each density model can exploit the characteristics of each pharmacological target and measure the quasi-distance between the ligands. Furthermore, we developed a random forest model from the KLD feature vectors to successfully predict DTIs for representative 17 targets (mean accuracy: 0.882, out-of-bag score estimate: 0.876, ROC AUC: 0.990). The method is applicable for 2D chemical similarity.

De Novo Prediction of Drug Targets and Candidates by Chemical Similarity-Guided Network-Based Inference

Identifying drug–target interactions is a crucial step in discovering novel drugs and for drug repositioning. Network-based methods have shown great potential thanks to the straightforward integration of information from different sources and the possibility of extracting novel information from the graph topology. However, despite recent advances, there is still an urgent need for efficient and robust prediction methods. Here, we present SimSpread, a novel method that combines network-based inference with chemical similarity. This method employs a tripartite drug–drug–target network constructed from protein–ligand interaction annotations and drug–drug chemical similarity on which a resource-spreading algorithm predicts potential biological targets for both known or failed drugs and novel compounds. We describe small molecules as vectors of similarity indices to other compounds, thereby providing a flexible means to explore diverse molecular representations. We show that our proposed method achieves high prediction performance through multiple cross-validation and time-split validation procedures over a series of datasets. In addition, we demonstrate that our method performed a balanced exploration of both chemical ligand space (scaffold hopping) and biological target space (target hopping). Our results suggest robust and balanced performance, and our method may be useful for predicting drug targets, virtual screening, and drug repositioning.

Unexpected similarity between HIV-1 reverse transcriptase and tumor necrosis factor binding sites revealed by computer vision

Rationalizing the identification of hidden similarities across the repertoire of druggable protein cavities remains a major hurdle to a true proteome-wide structure-based discovery of novel drug candidates. We recently described a new computational approach (ProCare), inspired by numerical image processing, to identify local similarities in fragment-based subpockets. During the validation of the method, we unexpectedly identified a possible similarity in the binding pockets of two unrelated targets, human tumor necrosis factor alpha (TNF-α) and HIV-1 reverse transcriptase (HIV-1 RT). Microscale thermophoresis experiments confirmed the ProCare prediction as two of the three tested and FDA-approved HIV-1 RT inhibitors indeed bind to soluble human TNF-α trimer. Interestingly, the herein disclosed similarity could be revealed neither by state-of-the-art binding sites comparison methods nor by ligand-based pairwise similarity searches, suggesting that the point cloud registration approach implemented in ProCare, is uniquely suited to identify local and unobvious similarities among totally unrelated targets.

Comprehensive strategies of machine-learning-based quantitative structure-activity relationship models

Early quantitative structure-activity relationship (QSAR) technologies have unsatisfactory versatility and accuracy in fields such as drug discovery because they are based on traditional machine learning and interpretive expert features. The development of Big Data and deep learning technologies significantly improve the processing of unstructured data and unleash the great potential of QSAR. Here we discuss the integration of wet experiments (which provide experimental data and reliable verification), molecular dynamics simulation (which provides mechanistic interpretation at the atomic/molecular levels), and machine learning (including deep learning) techniques to improve QSAR models. We first review the history of traditional QSAR and point out its problems. We then propose a better QSAR model characterized by a new iterative framework to integrate machine learning with disparate data input. Finally, we discuss the application of QSAR and machine learning to many practical research fields, including drug development and clinical trials.

Recent Advances in In Silico Target Fishing

In silico target fishing, whose aim is to identify possible protein targets for a query molecule, is an emerging approach used in drug discovery due its wide variety of applications. This strategy allows the clarification of mechanism of action and biological activities of compounds whose target is still unknown. Moreover, target fishing can be employed for the identification of off targets of drug candidates, thus recognizing and preventing their possible adverse effects. For these reasons, target fishing has increasingly become a key approach for polypharmacology, drug repurposing, and the identification of new drug targets. While experimental target fishing can be lengthy and difficult to implement, due to the plethora of interactions that may occur for a single small-molecule with different protein targets, an in silico approach can be quicker, less expensive, more efficient for specific protein structures, and thus easier to employ. Moreover, the possibility to use it in combination with docking and virtual screening studies, as well as the increasing number of web-based tools that have been recently developed, make target fishing a more appealing method for drug discovery. It is especially worth underlining the increasing implementation of machine learning in this field, both as a main target fishing approach and as a further development of already applied strategies. This review reports on the main in silico target fishing strategies, belonging to both ligand-based and receptor-based approaches, developed and applied in the last years, with a particular attention to the different web tools freely accessible by the scientific community for performing target fishing studies.

Chemical similarity methods for analyzing secondary metabolite structures

The relation that exists between the structure of a compound and its function is an integral part of chemoinformatics. The similarity principle states that “structurally similar molecules tend to have similar properties and similar molecules exert similar biological activities”. The similarity of the molecules can either be studied at the structure level or at the descriptor level (properties level). Generally, the objective of chemical similarity measures is to enhance prediction of the biological activities of molecules. In this article, an overview of various methods used to compare the similarity between metabolite structures has been provided, including two-dimensional (2D) and three-dimensional (3D) approaches. The focus has been on methods description; e.g. fingerprint-based similarity in which the molecules under study are first fragmented and their fingerprints are computed, 2D structural similarity by comparing the Tanimoto coefficients and Euclidean distances, as well as the use of physiochemical properties descriptor-based similarity methods. The similarity between molecules could also be measured by using data mining (clustering) techniques, e.g. by using virtual screening (VS)-based similarity methods. In this approach, the molecules with the desired descriptors or /and structures are screened from large databases. Lastly, SMILES-based chemical similarity search is an important method for studying the exact structure search, substructure search and also descriptor similarity. The use of a particular method depends upon the requirements of the researcher.

Enhancing Chemogenomics with Predictive Pharmacology

One of the grand challenges in contemporary chemical biology is the generation of a probe for every member of the human proteome. Probe selection and optimization strategies typically rely on experimental bioactivity data to determine the potency and selectivity of candidate molecules. However, this approach is profoundly limited by the sparsity of the known data, the annotation bias often found in the literature, and the cost of physical screening. Recent advancements in predictive pharmacology, such as the application of multitask and transfer learning, as well as the use of biologically motivated, structure-agnostic features to characterize molecules, should serve to mitigate these issues. Computational modeling likely offers the only cost-effective approach to substantially increasing the bioactivity annotation density both on the local and global scale and thus, we argue, will need to make a substantial contribution if the ambitious goals of probing the human proteome are to be realized in the foreseeable future.

Comparing a Query Compound with Drug Target Classes Using 3D-Chemical Similarity

3D similarity is useful in predicting the profiles of unprecedented molecular frameworks that are 2D dissimilar to known compounds. When comparing pairs of compounds, 3D similarity of the pairs depends on conformational sampling, the alignment method, the chosen descriptors, and the similarity coefficients. In addition to these four factors, 3D chemocentric target prediction of an unknown compound requires compound-target associations, which replace compound-to-compound comparisons with compound-to-target comparisons. In this study, quantitative comparison of query compounds to target classes (one-to-group) was achieved via two types of 3D similarity distributions for the respective target class with parameter optimization for the fitting models: (1) maximum likelihood (ML) estimation of queries, and (2) the Gaussian mixture model (GMM) of target classes. While Jaccard-Tanimoto similarity of query-to-ligand pairs with 3D structures (sampled multi-conformers) can be transformed into query distribution using ML estimation, the ligand pair similarity within each target class can be transformed into a representative distribution of a target class through GMM, which is hyperparameterized via the expectation-maximization (EM) algorithm. To quantify the discriminativeness of a query ligand against target classes, the Kullback-Leibler (K-L) divergence of each query was calculated and compared between targets. 3D similarity-based K-L divergence together with the probability and the feasibility index, (F_m), showed discriminative power with regard to some query-class associations. The K-L divergence of 3D similarity distributions can be an additional method for (1) the rank of the 3D similarity score or (2) the p-value of one 3D similarity distribution to predict the target of unprecedented drug scaffolds.

Similarity-Based Methods and Machine Learning Approaches for Target Prediction in Early Drug Discovery: Performance and Scope

Computational methods for predicting the macromolecular targets of drugs and drug-like compounds have evolved as a key technology in drug discovery. However, the established validation protocols leave several key questions regarding the performance and scope of methods unaddressed. For example, prediction success rates are commonly reported as averages over all compounds of a test set and do not consider the structural relationship between the individual test compounds and the training instances. In order to obtain a better understanding of the value of ligand-based methods for target prediction, we benchmarked a similarity-based method and a random forest based machine learning approach (both employing 2D molecular fingerprints) under three testing scenarios: a standard testing scenario with external data, a standard time-split scenario, and a scenario that is designed to most closely resemble real-world conditions. In addition, we deconvoluted the results based on the distances of the individual test molecules from the training data. We found that, surprisingly, the similarity-based approach generally outperformed the machine learning approach in all testing scenarios, even in cases where queries were structurally clearly distinct from the instances in the training (or reference) data, and despite a much higher coverage of the known target space.

Expanding the chemical diversity through microorganisms co-culture: Current status and outlook

Natural products (NPs) are considered as a cornerstone for the generation of bioactive leads in drug discovery programs. However, one of the major limitations of NP drug discovery program is "rediscovery" of known compounds, thereby hindering the rate of drug discovery efficiency. Therefore, in recent years, to overcome these limitations, a great deal of attention has been drawn towards understanding the role of microorganisms' co-culture in inducing novel chemical entities. Such induction could be related to activation of genes which might be silent or expressed at very low levels (below detection limit) in pure-strain cultures under normal laboratory conditions. In this review, chemical diversity of compounds isolated from microbial co-cultures, is discussed. For this purpose, chemodiversity has been represented as a chemical-structure network based on the "Tanimoto Structural Similarity Index". This highlights the huge structural diversity induced by microbial co-culture. In addition, the current trends in microbial co-culture research are highlighted. Finally, the current challenges (1 - induction monitoring, 2 - reproducibility, 3 - growth time effect and 4 - up-scaling for isolation purposes) are discussed. The information in this review will support researchers to design microbial co-culture strategies for future research efforts. In addition, guidelines for co-culture induction reporting are also provided to strengthen future reporting in this NP field.

DStruBTarget: Integrating Binding Affinity with Structure Similarity for Ligand-Binding Protein Prediction

Motivation: Identification of ligand-binding proteins is an important issue for drug development. Most of the current computational approach is developed only utilizing ligand structure similarity. However, the ligand structure similarity has failed to reflect the binding quality between the ligand and the target protein, which limited the performance of current methods. Results: The present study integrated two-dimensional (2D) and three-dimensional (3D) ligand structure similarity between query ligand and template with known ligand-protein binding affinity (BA) to identify proteins binding with the query ligand. This method is named as DStruBTarget. The performance of DStruBTarget was evaluated by 10-fold cross-validation in a dataset containing 9197 ligands and 1111 ligand-binding proteins (DBD dataset). This dataset was constructed by excluding the ligands with similar structures and the proteins with high sequence identity. The DStruBTarget achieved a hit rate of 77% in top 1 prediction, which is 4.80 and 3.00% better than the methods only using 2D structure similarity, and the method integrating 2D and 3D structure similarity (2D + 3D), respectively. An independent test of DStruBTarget was performed in a publicly available dataset constructed by SwissTargetPrediction. In this dataset, the top 1 hit rate of DStruBTarget reached 44.02%, which was better than the SwissTargetPrediction, and also outstands other methods, such as 2D, 3D, 2D + 3D, 2D integrating binding affinity (2D + BA), and 3D integrating binding affinity (3D + BA). DStruBTarget was compared to another newly published method HitPickV2 and achieved 52.17% hit rate of the top 1 prediction, which was significantly better than the result of HitpickV2 (30.43%). Finally, DStruBTarget was integrated with protein BLAST to predict the ligand-binding proteins not limited in a certain database. DStruBTarget with BLAST was tested in the DBD dataset. Its top 1 hit rate was 51.15%, which is lower than DStruBTarget without BLAST. Further comparison was on the ligands that bind to multiple numbers of proteins, which illustrated that DStruBTarget with BLAST performed better than without BLAST when the number of binding proteins of the query ligands is larger than six. Meanwhile, the prediction power of the DStruBTarget with BLAST in top 1 prediction was found to be positively correlated with the number of proteins binding with the query ligands, while the top 1 prediction power of DStruBTarget without BLAST was negatively correlated with the number of binding proteins for query ligands. Thus, DStruBTarget with BLAST is a potentially useful approach for predicting novel proteins for ligands that bind to multiple proteins.

Computational analysis of kinase inhibitor selectivity using structural knowledge

Motivation

Kinases play a significant role in diverse disease signaling pathways and understanding kinase inhibitor selectivity, the tendency of drugs to bind to off-targets, remains a top priority for kinase inhibitor design and clinical safety assessment. Traditional approaches for kinase selectivity analysis using biochemical activity and binding assays are useful but can be costly and are often limited by the kinases that are available. On the other hand, current computational kinase selectivity prediction methods are computational intensive and can rarely achieve sufficient accuracy for large-scale kinome wide inhibitor selectivity profiling.

Results

Here, we present a KinomeFEATURE database for kinase binding site similarity search by comparing protein microenvironments characterized using diverse physiochemical descriptors. Initial selectivity prediction of 15 known kinase inhibitors achieved an >90% accuracy and demonstrated improved performance in comparison to commonly used kinase inhibitor selectivity prediction methods. Additional kinase ATP binding site similarity assessment (120 binding sites) identified 55 kinases with significant promiscuity and revealed unexpected inhibitor cross-activities between PKR and FGFR2 kinases. Kinome-wide selectivity profiling of 11 kinase drug candidates predicted novel as well as experimentally validated off-targets and suggested structural mechanisms of kinase cross-activities. Our study demonstrated potential utilities of our approach for large-scale kinase inhibitor selectivity profiling that could contribute to kinase drug development and safety assessment.

Availability and implementation

The KinomeFEATURE database and the associated scripts for performing kinase pocket similarity search can be downloaded from the Stanford SimTK website (https://simtk.org/projects/kdb).

Supplementary information

Supplementary data are available at Bioinformatics online.

Dissecting the mechanisms of cell division

Cell division is a highly regulated and carefully orchestrated process. Understanding the mechanisms that promote proper cell division is an important step toward unraveling important questions in cell biology and human health. Early studies seeking to dissect the mechanisms of cell division used classical genetics approaches to identify genes involved in mitosis and deployed biochemical approaches to isolate and identify proteins critical for cell division. These studies underscored that post-translational modifications and cyclin-kinase complexes play roles at the heart of the cell division program. Modern approaches for examining the mechanisms of cell division, including the use of high-throughput methods to study the effects of RNAi, cDNA, and chemical libraries, have evolved to encompass a larger biological and chemical space. Here, we outline some of the classical studies that established a foundation for the field and provide an overview of recent approaches that have advanced the study of cell division.

Leukemia Cell Cycle Chemical Profiling Identifies the G2-Phase Leukemia Specific Inhibitor Leusin-1

Targeting the leukemia proliferation cycle has been a successful approach to developing antileukemic therapies. However, drug screening efforts to identify novel antileukemic agents have been hampered by the lack of a suitable high-throughput screening platform for suspension cells that does not rely on flow-cytometry analyses. We report the development of a novel leukemia cell-based high-throughput chemical screening platform for the discovery of cell cycle phase specific inhibitors that utilizes chemical cell cycle profiling. We have used this approach to analyze the cell cycle response of acute lymphoblastic leukemia CCRF-CEM cells to each of 181420 druglike compounds. This approach yielded cell cycle phase specific inhibitors of leukemia cell proliferation. Further analyses of the top G2-phase and M-phase inhibitors identified the leukemia specific inhibitor 1 (Leusin-1). Leusin-1 arrests cells in G2 phase and triggers an apoptotic cell death. Most importantly, Leusin-1 was more active in acute lymphoblastic leukemia cells than other types of leukemias, non-blood cancers, or normal cells and represents a lead molecule for developing antileukemic drugs.

Pocket similarity identifies selective estrogen receptor modulators as microtubule modulators at the taxane site

Taxanes are a family of natural products with a broad spectrum of anticancer activity. This activity is mediated by interaction with the taxane site of beta-tubulin, leading to microtubule stabilization and cell death. Although widely used in the treatment of breast cancer and other malignancies, existing taxane-based therapies including paclitaxel and the second-generation docetaxel are currently limited by severe adverse effects and dose-limiting toxicity. To discover taxane site modulators, we employ a computational binding site similarity screen of > 14,000 drug-like pockets from PDB, revealing an unexpected similarity between the estrogen receptor and the beta-tubulin taxane binding pocket. Evaluation of nine selective estrogen receptor modulators (SERMs) via cellular and biochemical assays confirms taxane site interaction, microtubule stabilization, and cell proliferation inhibition. Our study demonstrates that SERMs can modulate microtubule assembly and raises the possibility of an estrogen receptor-independent mechanism for inhibiting cell proliferation.

Taxanes are natural products which bind beta-tubulin, stabilize microtubules and have a broad spectrum of anticancer activity. Here authors employ a computational binding site similarity screen and cell-based assays to reveal a SERM cross-reactivity between the estrogen receptor and the beta-tubulin taxane binding pocket.

Reverse Screening Methods to Search for the Protein Targets of Chemopreventive Compounds

This article is a systematic review of reverse screening methods used to search for the protein targets of chemopreventive compounds or drugs. Typical chemopreventive compounds include components of traditional Chinese medicine, natural compounds and Food and Drug Administration (FDA)-approved drugs. Such compounds are somewhat selective but are predisposed to bind multiple protein targets distributed throughout diverse signaling pathways in human cells. In contrast to conventional virtual screening, which identifies the ligands of a targeted protein from a compound database, reverse screening is used to identify the potential targets or unintended targets of a given compound from a large number of receptors by examining their known ligands or crystal structures. This method, also known as in silico or computational target fishing, is highly valuable for discovering the target receptors of query molecules from terrestrial or marine natural products, exploring the molecular mechanisms of chemopreventive compounds, finding alternative indications of existing drugs by drug repositioning, and detecting adverse drug reactions and drug toxicity. Reverse screening can be divided into three major groups: shape screening, pharmacophore screening and reverse docking. Several large software packages, such as Schrödinger and Discovery Studio; typical software/network services such as ChemMapper, PharmMapper, idTarget, and INVDOCK; and practical databases of known target ligands and receptor crystal structures, such as ChEMBL, BindingDB, and the Protein Data Bank (PDB), are available for use in these computational methods. Different programs, online services and databases have different applications and constraints. Here, we conducted a systematic analysis and multilevel classification of the computational programs, online services and compound libraries available for shape screening, pharmacophore screening and reverse docking to enable non-specialist users to quickly learn and grasp the types of calculations used in protein target fishing. In addition, we review the main features of these methods, programs and databases and provide a variety of examples illustrating the application of one or a combination of reverse screening methods for accurate target prediction.

Machine learning in chemoinformatics and drug discovery

Chemoinformatics is an established discipline focusing on extracting, processing and extrapolating meaningful data from chemical structures. With the rapid explosion of chemical 'big' data from HTS and combinatorial synthesis, machine learning has become an indispensable tool for drug designers to mine chemical information from large compound databases to design drugs with important biological properties. To process the chemical data, we first reviewed multiple processing layers in the chemoinformatics pipeline followed by the introduction of commonly used machine learning models in drug discovery and QSAR analysis. Here, we present basic principles and recent case studies to demonstrate the utility of machine learning techniques in chemoinformatics analyses; and we discuss limitations and future directions to guide further development in this evolving field.

Microtubins: a novel class of small synthetic microtubule targeting drugs that inhibit cancer cell proliferation

Microtubule targeting drugs like taxanes, vinca alkaloids, and epothilones are widely-used and effective chemotherapeutic agents that target the dynamic instability of microtubules and inhibit spindle functioning. However, these drugs have limitations associated with their production, solubility, efficacy and unwanted toxicities, thus driving the need to identify novel antimitotic drugs that can be used as anticancer agents. We have discovered and characterized the Microtubins (Microtubule inhibitors), a novel class of small synthetic compounds, which target tubulin to inhibit microtubule polymerization, arrest cancer cells predominantly in mitosis, activate the spindle assembly checkpoint and trigger an apoptotic cell death. Importantly, the Microtubins do not compete for the known vinca or colchicine binding sites. Additionally, through chemical synthesis and structure-activity relationship studies, we have determined that specific modifications to the Microtubin phenyl ring can activate or inhibit its bioactivity. Combined, these data define the Microtubins as a novel class of compounds that inhibit cancer cell proliferation by perturbing microtubule polymerization and they could be used to develop novel cancer therapeutics.

Computational Cell Cycle Profiling of Cancer Cells for Prioritizing FDA-Approved Drugs with Repurposing Potential

Discovery of first-in-class medicines for treating cancer is limited by concerns with their toxicity and safety profiles, while repurposing known drugs for new anticancer indications has become a viable alternative. Here, we have developed a new approach that utilizes cell cycle arresting patterns as unique molecular signatures for prioritizing FDA-approved drugs with repurposing potential. As proof-of-principle, we conducted large-scale cell cycle profiling of 884 FDA-approved drugs. Using cell cycle indexes that measure changes in cell cycle profile patterns upon chemical perturbation, we identified 36 compounds that inhibited cancer cell viability including 6 compounds that were previously undescribed. Further cell cycle fingerprint analysis and 3D chemical structural similarity clustering identified unexpected FDA-approved drugs that induced DNA damage, including clinically relevant microtubule destabilizers, which was confirmed experimentally via cell-based assays. Our study shows that computational cell cycle profiling can be used as an approach for prioritizing FDA-approved drugs with repurposing potential, which could aid the development of cancer therapeutics.

DRABAL: novel method to mine large high-throughput screening assays using Bayesian active learning

Background

Mining high-throughput screening (HTS) assays is key for enhancing decisions in the area of drug repositioning and drug discovery. However, many challenges are encountered in the process of developing suitable and accurate methods for extracting useful information from these assays. Virtual screening and a wide variety of databases, methods and solutions proposed to-date, did not completely overcome these challenges. This study is based on a multi-label classification (MLC) technique for modeling correlations between several HTS assays, meaning that a single prediction represents a subset of assigned correlated labels instead of one label. Thus, the devised method provides an increased probability for more accurate predictions of compounds that were not tested in particular assays.

Results

Here we present DRABAL, a novel MLC solution that incorporates structure learning of a Bayesian network as a step to model dependency between the HTS assays. In this study, DRABAL was used to process more than 1.4 million interactions of over 400,000 compounds and analyze the existing relationships between five large HTS assays from the PubChem BioAssay Database. Compared to different MLC methods, DRABAL significantly improves the F₁Score by about 22%, on average. We further illustrated usefulness and utility of DRABAL through screening FDA approved drugs and reported ones that have a high probability to interact with several targets, thus enabling drug-multi-target repositioning. Specifically DRABAL suggests the Thiabendazole drug as a common activator of the NCP1 and Rab-9A proteins, both of which are designed to identify treatment modalities for the Niemann–Pick type C disease.

Conclusion

We developed a novel MLC solution based on a Bayesian active learning framework to overcome the challenge of lacking fully labeled training data and exploit actual dependencies between the HTS assays. The solution is motivated by the need to model dependencies between existing experimental confirmatory HTS assays and improve prediction performance. We have pursued extensive experiments over several HTS assays and have shown the advantages of DRABAL. The datasets and programs can be downloaded from https://figshare.com/articles/DRABAL/3309562.Graphical abstract